Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnly/idempotent annotations, the description discloses the full return shape, polling behavior, terminal status handling, and failure modes such as montage_failed and montage_refunded when only raw shots are delivered. This is exactly the behavioral context an agent needs for a complex read operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The content is useful but delivered as a dense run-on paragraph with parentheticals and semicolon-separated clauses. It is front-loaded with what the tool returns, but the structure makes it harder to scan than a bulleted or clearly segmented description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the absence of an output schema, the description thoroughly covers the return payload, progress states, quality/fix-offer fields, polling lifecycle, final video identifier, and failure/refund states. Nothing critical for correct invocation appears to be missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, but the description compensates by labeling the nested arguments: id is the project id and shoot_id is the shoot id. It does not explain expected formats or where to obtain those identifiers, so it stops short of a 5.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly defines the resource as a multi-shot plan produced by plan_shoot or plan_video and enumerates exactly what the tool returns: per-shot duration/credits, montage_credits, totals, progress, quality report, fix offer, and English directions. This is a specific verb-and-resource statement that lets an agent distinguish this retrieval tool from siblings like accept_shoot or answer_offer.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit timing guidance: 'Poll it after accept_shoot until status=delivered' and explains that english_directions_needed texts are sent via accept_shoot / answer_offer. It does not explicitly state when not to use this tool or name an alternative retrieval tool, which keeps it from a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.